SP-P2: Machine Learning and Acoustic Modeling |
| Session Type: Poster |
| Time: Tuesday, March 27, 14:00 - 16:00 |
| Location: Poster Area B
|
| Session Chairs: Patrick Nguyen, Google, Inc. and Takahiro Shinozaki, Chiba University
|
| |
|
SP-P2.1: SEQUENTIAL DEEP BELIEF NETWORKS
|
| Galen Andrew; University of Washington
|
| Jeff Bilmes; University of Washington
|
| |
|
SP-P2.2: MULTILINGUAL MLP FEATURES FOR LOW-RESOURCE LVCSR SYSTEMS
|
| Samuel Thomas; The Johns Hopkins University
|
| Sriram Ganapathy; The Johns Hopkins University
|
| Hynek Hermansky; The Johns Hopkins University
|
| |
|
SP-P2.3: UNDERSTANDING HOW DEEP BELIEF NETWORKS PERFORM ACOUSTIC MODELLING
|
| Abdel-Rahman Mohamed; University of Toronto
|
| Geoffrey Hinton; University of Toronto
|
| Gerald Penn; University of Toronto
|
| |
|
SP-P2.4: APPLYING CONVOLUTIONAL NEURAL NETWORKS CONCEPTS TO HYBRID NN-HMM MODEL FOR SPEECH RECOGNITION
|
| Ossama Abdel-Hamid; York University
|
| Abdel-Rahman Mohamed; University of Toronto
|
| Hui Jiang; York University
|
| Gerald Penn; University of Toronto
|
| |
|
SP-P2.5: A FAST COMPRESSIVE SENSING APPROACH FOR PHONEME CLASSIFICATION
|
| Armin Saeb; Islamic Azad University, Shahr-e-Rey Branch
|
| Farbod Razzazi; Islamic Azad University, Science and Research Branch
|
| |
|
SP-P2.6: CLASSIFICATION MARGIN FOR IMPROVED CLASS-BASED SPEECH RECOGNITION PERFORMANCE
|
| Denis Jouvet; INRIA - LORIA
|
| Nicolas Vinuesa; INRIA - LORIA
|
| |
|
SP-P2.7: UNSEEN NOISE ROBUST SPEECH RECOGNITION USING ADAPTIVE PIECEWISE LINEAR TRANSFORMATION
|
| Keigo Chijiiwa; The University of Tokyo
|
| Masayuki Suzuki; The University of Tokyo
|
| Nobuaki Minematsu; The University of Tokyo
|
| Keikichi Hirose; The University of Tokyo
|
| |
|
SP-P2.8: A TANDEM CONNECTIONIST MODEL USING COMBINATION OF MULTI-SCALE SPECTRO-TEMPORAL FEATURES FOR ACOUSTIC EVENT DETECTION
|
| Miquel Espi; The University of Tokyo
|
| Masakiyo Fujimoto; NTT Corporation
|
| Daisuke Saito; The University of Tokyo
|
| Nobutaka Ono; National Institute of Informatics
|
| Shigeki Sagayama; The University of Tokyo
|
| |
|
SP-P2.9: FACTORIAL HIDDEN RESTRICTED BOLTZMANN MACHINES FOR NOISE ROBUST SPEECH RECOGNITION
|
| Steven Rennie; IBM
|
| Petr Fousek; IBM
|
| Pierre Dognin; IBM
|
| |
|
SP-P2.10: STRANDED GAUSSIAN MIXTURE HIDDEN MARKOV MODELS FOR ROBUST SPEECH RECOGNITION
|
| Yong Zhao; Georgia Institute of Technology
|
| Biing-Hwang (Fred) Juang; Georgia Institute of Technology
|
| |
|
SP-P2.11: LASSO ENVIRONMENT MODEL COMBINATION FOR ROBUST SPEECH RECOGNITION
|
| Xiong Xiao; Nanyang Technological University
|
| Jinyu Li; Microsoft Corporation
|
| Eng-Siong Chng; Nanyang Technological University
|
| Haizhou Li; Institute for Infocomm Research
|
| |
|
SP-P2.12: EASY DOES IT: ROBUST SPECTRO-TEMPORAL MANY-STREAM ASR WITHOUT FINE TUNING STREAMS
|
| Suman Ravuri; ICSI/University of California at Berkeley
|
| Nelson Morgan; ICSI/University of California at Berkeley
|
| |